lkml.org 
[lkml]   [2016]   [May]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] cyclictest: stop any tracing after hitting a breaktrace threshold
On Tue, 3 May 2016 12:59:53 -0500
Clark Williams <williams@redhat.com> wrote:

> John,
>
> This patch is against the devel/v0.98 branch. It turns off tracing in the tracemark() so that we don't lose information about what was going on when we hit the latency:
>
>
> The current logic of using --tracemark and --notrace works for running
> cyclictest with trace-cmd, but even if we are not doing any trace
> manipulation in cyclictest, we still need to stop tracing when we hit a
> breaktrace threshold (i.e. -b <n>).

Does it solve the problem for you if you revert ba4dd1bf54 and start
cyclictest with:

# cyclictest [...] -bX

Or with:

# cyclictest [...] -bX --tracemark

Also, how do I reproduce your issue? Are you doing tracing by hand?

More comments below.

>
> Modify startup logic to hold open file descriptors for the tracemark file
> *and* the tracing_on file. When we hit a threshold and call the tracemark()
> function, write the marker to the trace buffers and then write a "0\n" to
> the tracing_on file to turn off tracing, otherwise we lose the information
> immediately prior to the point where we hit the latency.
>
> Signed-off-by: Clark Williams <williams@redhat.com>
> ---
> src/cyclictest/cyclictest.c | 32 ++++++++++++++++++++++++++------
> 1 file changed, 26 insertions(+), 6 deletions(-)
>
> diff --git a/src/cyclictest/cyclictest.c b/src/cyclictest/cyclictest.c
> index 902167010416..00e5f3d59a5b 100644
> --- a/src/cyclictest/cyclictest.c
> +++ b/src/cyclictest/cyclictest.c
> @@ -489,7 +489,12 @@ static void tracemark(char *fmt, ...)
> va_start(ap, fmt);
> len = vsnprintf(tracebuf, TRACEBUFSIZ, fmt, ap);
> va_end(ap);
> +
> + /* write the tracemark message */
> write(tracemark_fd, tracebuf, len);
> +
> + /* now stop any trace */
> + write(trace_fd, "0\n", 2);
> }

We do tracing(0) when we hit the latency threshold, so I don't
think this is necessary.

However, have you checked that writing to tracing_on won't break
trace-cmd when it exec()ed cyclictest?

>
>
> @@ -535,13 +540,28 @@ static void open_tracemark_fd(void)
> {
> char path[MAX_PATH];
>
> - if (tracemark_fd >= 0)
> - return;
> + /*
> + * open the tracemark file if it's not already open
> + */
> + if (tracemark_fd < 0) {
> + sprintf(path, "%s/%s", fileprefix, "trace_marker");
> + tracemark_fd = open(path, O_WRONLY);
> + if (tracemark_fd < 0) {
> + warn("unable to open trace_marker file: %s\n", path);
> + return;
> + }
> + }
>
> - sprintf(path, "%s/%s", fileprefix, "trace_marker");
> - tracemark_fd = open(path, O_WRONLY);
> - if (tracemark_fd < 0)
> - warn("unable to open trace_marker file: %s\n", path);
> + /*
> + * if we're not tracing and the tracing_on fd is not open,
> + * open the tracing_on file so that we can stop the trace
> + * if we hit a breaktrace threshold
> + */
> + if (notrace && trace_fd < 0) {
> + sprintf(path, "%s/%s", fileprefix, "tracing_on");
> + if ((trace_fd = open(path, O_WRONLY)) < 0)
> + warn("unable to open tracing_on file: %s\n", path);
> + }
> }
>
> static void debugfs_prepare(void)

\
 
 \ /
  Last update: 2016-05-03 22:01    [W:0.068 / U:0.960 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site